Related papers: Separating Semantic Competition from Context Lengt…
Retrieval-augmented generation (RAG) systems are increasingly used to analyze complex policy documents, but achieving sufficient reliability for expert usage remains challenging in domains characterized by dense legal language and evolving,…
Multilingual vision-language models have made significant strides in image captioning, yet they still lag behind their English counterparts due to limited multilingual training data and costly large-scale model parameterization.…
Retriever-augmented generation (RAG) has become a widely adopted approach for enhancing the factual accuracy of large language models (LLMs). While current benchmarks evaluate the performance of RAG methods from various perspectives, they…
Recent investigations into effective context lengths of modern flagship large language models (LLMs) have revealed major limitations in effective question answering (QA) and reasoning over long and complex contexts for even the largest and…
The performance of Open-Domain Question Answering (ODQA) retrieval systems can exhibit sub-optimal behavior, providing text excerpts with varying degrees of irrelevance. Unfortunately, many existing ODQA datasets lack examples specifically…
Retrieval-Augmented Generation (RAG) systems commonly suffer from Knowledge Conflicts, where retrieved external knowledge contradicts the inherent, parametric knowledge of large language models (LLMs). It adversely affects performance on…
Large language models (LLMs) have transformed natural language processing (NLP), enabling diverse applications by integrating large-scale pre-trained knowledge. However, their static knowledge limits dynamic reasoning over external…
Reinforcement learning (RL) based on the final answer's reward has driven recent progress in small language models (SLMs) on reasoning-heavy tasks such as math and code. However, applying the same techniques to retrieval-augmented…
Retrieval-Augmented Generation (RAG) couples document retrieval with large language models (LLMs). While scaling generators often improves accuracy, it also increases inference and deployment overhead. We study an orthogonal axis: enlarging…
Retrieval-Augmented Generation (RAG) has been used in question answering (QA) systems to improve performance when relevant information is in one (single-hop) or multiple (multi-hop) passages. However, many real life scenarios (e.g. dealing…
Retrieval-Augmented Generation (RAG) has emerged as a standard framework for knowledge-intensive NLP tasks, combining large language models (LLMs) with document retrieval from external corpora. Despite its widespread use, most RAG pipelines…
Reinforcement learning has recently shown promise in improving retrieval-augmented generation (RAG). Despite these advances, its effectiveness in multi-hop question answering (QA) remains limited by two fundamental limitations: (i) global…
Software engineers are increasingly adding semantic search capabilities to applications using a strategy known as Retrieval Augmented Generation (RAG). A RAG system involves finding documents that semantically match a query and then passing…
With the adoption of retrieval-augmented generation (RAG), large language models (LLMs) are expected to ground their generation to the retrieved contexts. Yet, this is hindered by position bias of LLMs, failing to evenly attend to all…
Retrieval-augmented generation (RAG) for language models significantly improves language understanding systems. The basic retrieval-then-read pipeline of response generation has evolved into a more extended process due to the integration of…
Existing research on Retrieval-Augmented Generation (RAG) primarily focuses on improving overall question-answering accuracy, often overlooking the quality of sub-claims within generated responses. Recent methods that attempt to improve RAG…
We address the task of predicting the gain of using RAG (retrieval augmented generation) for question answering with respect to not using it. We study the performance of a few pre-retrieval and post-retrieval predictors originally devised…
Passage reranking is a critical task in various applications, particularly when dealing with large volumes of documents. Existing neural architectures have limitations in retrieving the most relevant passage for a given question because the…
Extending context windows (i.e., Long Context, LC) and using retrievers to selectively access relevant information (i.e., Retrieval-Augmented Generation, RAG) are the two main strategies to enable LLMs to incorporate extremely long external…
This paper considers the reading comprehension task in which multiple documents are given as input. Prior work has shown that a pipeline of retriever, reader, and reranker can improve the overall performance. However, the pipeline system is…